US4567610A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method of and apparatus for pattern recognition
Assignee: Wayland Research Inc
•
Filing: 1982-07-22
•
Granted: 1986-01-28
•
Expires: 2002-07-22
Abstract
Abstract A method of and an apparatus for analysis of patterns both in static and dynamic modes. A test histogram is described in terms of the optimum code described for a reference histogram.
Inventors
- 👤 Robert K. McConnell
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 11:29
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/40; G06V10/46
Claims Analysis
Total Claims: 55
Claim 1
Independent Claim
117 words
A method of recognizing a pattern in a test object, said method comprising the steps of: specifying properties characteristic of said pattern; specifying discrete ranges of values of said properties; measuring the values of said properties in said test object; arranging the measured values in at least one test histogram; determining a reference set of values of said properties and arranging said set as at least a first reference histogram; and comparing said test and reference histograms by determination of the value of a function which provides a measure of the amount of information necessary to express said at least one test histogram in terms of the optimum code for describing at least said first reference histogram.
Claim 2
Independent Claim
117 words
A method of recognizing a pattern in a test object, said method comprising the steps of: specifying properties characteristic of said pattern; specifying discrete ranges of values of said properties; measuring the values of said properties in said test object; arranging the measured values in at least one test histogram; determining a reference set of values of said properties and arranging said set as at least a first reference histogram; and comparing said test and reference histograms by determination of the value of a function which provides a measure of the amount of information necessary to express said at least one test histogram in terms of the optimum code for describing at least said first reference histogram.
Claim 3
Dependent Claim
32 words
A method as defined in claim 1 including the steps of digitizing said reference set of values and said measured values prior to aranging same in said respective reference and test histograms.
Claim 4
Dependent Claim
109 words
A method as defined in claim 1 wherein said step of determining said reference set of values includes arranging said set in a plurality of reference histograms, said step of comparing includes comparing said plurality of reference histograms with said test histogram by determination of, for each such comparison, the value of a function which provides a measure of the amount of information necessary to express said test histogram in terms of each of said reference histograms; and said method further including the step of selecting that one of said plurality of reference histograms which provides for said function a value bearing a predetermined relationship to a desired value.
Claim 5
Dependent Claim
138 words
A method as defined in claim 1 wherein said test object is one of a plurality of test objects, said step of measuring includes measuring the values of said properties for each of said test objects, said step of arranging includes arranging the measured values of said properties in a plurality of test histograms, said step of comparing includes comparing said plurality of test histograms with said first reference histogram by determination, for each such comparison, of the value of a function which provides a measure of the amount of information necessary to express each of said test histograms in terms of said first reference histogram; and said method further including the step of selecting that one of said plurality of test histograms which provides for said function a value bearing a predetermined relationship to a desired value.
Claim 6
Independent Claim
134 words
A method of recognizing a pattern in a test object, said method comprising the steps of: specifying properties characteristic of said pattern; specifying discrete ranges of values of said properties, measuring the values of said properties in said test object; determining the number of such measured values falling in each said discrete range and arranging such number in each said range in at least one test histogram; determining a reference set of values of said properties and arranging said set as at least a first reference histogram; and comparing said test and reference histograms by determination of the value of a function which provides a measure of the amount of information necessary to express said at least one test histogram in terms of the optimum code for describing at least said first reference histogram.
Claim 7
Independent Claim
134 words
A method of recognizing a pattern in a test object, said method comprising the steps of: specifying properties characteristic of said pattern; specifying discrete ranges of values of said properties, measuring the values of said properties in said test object; determining the number of such measured values falling in each said discrete range and arranging such number in each said range in at least one test histogram; determining a reference set of values of said properties and arranging said set as at least a first reference histogram; and comparing said test and reference histograms by determination of the value of a function which provides a measure of the amount of information necessary to express said at least one test histogram in terms of the optimum code for describing at least said first reference histogram.
Claim 8
Dependent Claim
43 words
A method as defined in claim 5 wherein said step of determining said reference set of values comprises taking a plurality of measurements of one or more of said objects and summing said plurality of measurements to derive said reference set of values.
Claim 9
Dependent Claim
49 words
A method as defined in claim 5 wherein said measured values are arranged into a plurality of said test histograms, and said step of comparing determines which of said plurality of test histograms when compared to said at least one reference histogram provides a minimum value of said function.
Claim 10
Dependent Claim
51 words
A method as defined in claim 5 wherein said reference set of values is arranged into a plurality of said reference histograms, and said step of comparing determines which of said plurality of reference histograms when compared with said at least one test histogram provides a minimum value of said function.
Claim 11
Dependent Claim
23 words
A method as defined in claim 1 including the step of generating a signal, based upon the result of the comparison of histograms.
Claim 12
Dependent Claim
38 words
A method as defined in claim 1 wherein said properties comprise (a) positions in a field of view, and (b) the nature of a signal arising from a unit area of said field at each of said positions.
Claim 13
Dependent Claim
29 words
A method as defined in claim 10 wherein each of said positions in said field of view is defined in terms of location within a rectangular array of positions.
Claim 14
Dependent Claim
31 words
A method as defined in claim 10 wherein each of said positions in said field of view is defined in terms of location in one of a series of concentric rings.
Claim 15
Dependent Claim
33 words
A method as defined in claim 10 wherein each of said positions in said field of view is defined in terms of location within an angular sector around a center within said field.
Claim 16
Dependent Claim
17 words
A method as defined in claim 10 wherein said nature of said signal is the intensity thereof.
Claim 17
Dependent Claim
18 words
A method as defined in claim 10 wherein the nature of said signal is the wavelength range thereof.
Claim 18
Dependent Claim
26 words
A method as defined in claim 10 wherein each of said positions in said field of view is defined in terms of location in adjacent rows.
Claim 19
Dependent Claim
19 words
A method as defined in claim 10 wherein each of said positions is defined in terms of adjacent columns.
Claim 20
Dependent Claim
31 words
A method as defined in claim 10 wherein said properties comprise the number of selected points in said field of view having a value falling within each of said discrete ranges.
Claim 21
Dependent Claim
27 words
A method as defined in claim 1 wherein said properties comprise (a) edges of said test object and (b) the slope of said edges at selected points.
Claim 22
Dependent Claim
28 words
A method as defined in claim 1 wherein the values in at least one of said histograms are sums of weighted values of a given sequence of values.
Claim 23
Dependent Claim
17 words
A method as defined in claim 20 wherein said at least one histogram is said test histogram.
Claim 24
Dependent Claim
19 words
A method as defined in claim 20 wherein said at least one of said histograms is said reference histogram.
Claim 25
Dependent Claim
27 words
A method as defined in claim 1 wherein the values in both said refence and test histograms are sums of weighted values of given sequences of values.
Claim 26
Dependent Claim
81 words
A method as defined in claim 1 wherein said function is I(T:R) and is defined as ##EQU11## where T is a test histogram; R is a reference histogram; I(T:R) is the information of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; and Q is the number of different symbols in T.
Claim 27
Dependent Claim
77 words
A method as defined in claim 1 wherein said function is I(T:T) and is defined as ##EQU12## where T is a test histogram; I(T:T) is the information of T expressed in terms of T; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i ' is the probability of the ith symbol occurring in T: and Q is the number of different symbols in T.
Claim 28
Dependent Claim
82 words
A method as defined in claim 1 wherein said function is H(T:R) and is defined as ##EQU13## where T is a test histogram; R is a reference histogram; H(T:R) is the entropy of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; and ##EQU14##
Claim 29
Dependent Claim
78 words
A method as defined in claim 1 wherein said function is H(T:T) and is defined as ##EQU15## where T is a test histogram; H(T:T) is the entropy of T expressed in terms of T; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; P i ' is the probability of the ith symbol occurring in T; Q is the number of different symbols in T; and ##EQU16##
Claim 30
Dependent Claim
102 words
A method as defined in claim 1 wherein said function is I(T:R)-I(T:T) where ##EQU17## T is a test histogram; R is a reference histogram; I(T:R) is the information of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU18## I(T:T) is the information of T expressed in terms of T, and p i ' is the probability of the ith symbol occurring in T.
Claim 31
Dependent Claim
101 words
A method as defined in claim 1 wherein said function is H(T:R)-H(T:T) where ##EQU19## T is a test histogram; R is a reference histogram; H(T:R) is the entropy of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU20## H(T:T) is the entropy of T expressed in terms of T; and p i 'is the probability of the ith symbol occurring in T.
Claim 32
Dependent Claim
102 words
A method as defined in claim 1 wherein said function is I(T:R)-I(R:R) where ##EQU21## T is a test histogram; R is a reference histogram; I(T:R) is the information of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU22## I(R:R) is the information of R expressed in terms of R, and n i is the number of occurrences of the ith symbol in R.
Claim 33
Dependent Claim
102 words
A method as defined in claim 1 wherein said function is H(T:R)-H(R:R) where ##EQU23## T is a test histogram; R is a reference histogram; H(T:R) is the entropy of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU24## H(R:R) is the entropy of R expressed in terms of R; ##EQU25## n i is the number of occurrences of the ith symbol in R.
Claim 34
Dependent Claim
26 words
A method as defined in claim 9 wherein said signal is generated when said value of said function is found to be below a predetermined value.
Claim 35
Dependent Claim
22 words
A method as defined in claim 9 wherein said signal is generated when said value is found to be at a minimum.
Claim 36
Dependent Claim
22 words
A method as defined in claim 9 wherein said signal is generated when said value is found to be at a maximum.
Claim 37
Dependent Claim
23 words
A method as defined in claim 9 wherein said signal is generated when said value is found to be above a predetermined value.
Claim 38
Dependent Claim
54 words
A method as defined in claim 1 wherein the step of measuring includes establishing test object measurement coordinates to define said values of properties in said test object, and further wherein the value of said function is assigned to locations among said test object measurement coordinates so as to produce an enhanced test object.
Claim 39
Dependent Claim
150 words
A method as defined in claim 36 including the steps of forming a digitized image of said test object; and wherein said function is H(T:T) and is defined as ##EQU26## wherein T is a test histogram; H(T:T) is the entropy of T expressed in terms of T; b is the base of the logarithm; m i is the number of occurrences is the ith symbol in T; p i ' is the probability of the ith symbol occurring in T; Q is the number of different symbols in T; ##EQU27## and wherein said properties are (a) position in a field of view of said test object, and (b) the nature of the signals arising from said position, said comparison values are assigned to a position at the geometric center of said field of view, and said field is scanned over the original digitized image to produce an enhanced digitized image.
Claim 40
Dependent Claim
112 words
Apparatus for recognizing a pattern in a test object, said apparatus comprising, in combination: means for measuring in said test object the values of specified properties characteristic of said pattern, means for arranging the measured values of said properties in at least one test histogram; means for storing a reference set of values of said specified properties as at least a first reference histogram; means for comparing said test and reference histograms by determination of the value of a function which provides a measure of the amount of information necessary to express said at least one test histogram in terms of the optimum code for describing at least said first reference histogram.
Claim 41
Dependent Claim
112 words
Apparatus for recognizing a pattern in a test object, said apparatus comprising, in combination: means for measuring in said test object the values of specified properties characteristic of said pattern, means for arranging the measured values of said properties in at least one test histogram; means for storing a reference set of values of said specified properties as at least a first reference histogram; means for comparing said test and reference histograms by determination of the value of a function which provides a measure of the amount of information necessary to express said at least one test histogram in terms of the optimum code for describing at least said first reference histogram.
Claim 42
Dependent Claim
30 words
Apparatus as defined in claim 38 including means for digitizing said reference set of values and said measured values prior to aranging same in said respective reference and test histograms.
Claim 43
Dependent Claim
17 words
Apparatus according to claim 38 wherein said means for measuring comprises means for scanning said test object.
Claim 44
Dependent Claim
14 words
Apparatus according to claim 40 wherein said means for scanning is an optical scanner.
Claim 45
Dependent Claim
17 words
Apparatus according to claim 39 wherein said means for arranging said measured values comprises digital counter means.
Claim 46
Dependent Claim
17 words
Apparatus according to claim 39 wherein said means for storing said reference set comprises digital memory means.
Claim 47
Dependent Claim
22 words
Apparatus according to claim 39 wherein said means for comparing comprises digital computer means programmed to determine the value of said function.
Claim 48
Dependent Claim
79 words
Apparatus according to claim 38 wherein said function is I(T:R) and is defined as ##EQU28## where T is a test histogram; R is a reference histogram; I(T:R) is the information of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; and Q is the number of different symbols in T.
Claim 49
Dependent Claim
75 words
Apparatus according to claim 38 wherein said function is I(T:T) and is defined as ##EQU29## where T is a test histogram; I(T:T) is the information of T expressed in terms of T; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i ' is the probability of the ith symbol occurring in T: and Q is the number of different symbols in T.
Claim 50
Dependent Claim
80 words
Apparatus according to claim 38 wherein said function is H(T:R) and is defined as ##EQU30## where T is a test histogram; R is a reference histogram; H(T:R) is the entropy of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; and ##EQU31##
Claim 51
Dependent Claim
76 words
Apparatus according to claim 38 wherein said function is H(T:T) and is defined as ##EQU32## where T is a test histogram; H(T:T) is the entropy of T expressed in terms of T; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i ' is the probability of the ith symbol occurring in T; Q is the number of different symbols in T; and ##EQU33##
Claim 52
Dependent Claim
100 words
Apparatus according to claim 38 wherein said function is I(T:R)-I(T:T) where ##EQU34## T is a test histogram; R is a reference histogram; I(T:R) is the information of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU35## I(T:T) is the information of T expressed in terms of T; and p i ' is the probability of the ith symbol occurring in T.
Claim 53
Dependent Claim
100 words
Apparatus according to claim 38 wherein said function is H(T:R)-H(T:T) where ##EQU36## T is a test histogram; R is a reference histogram; H(T:R) is the entropy of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU37## H(T:T) is the entropy of T expressed in terms of T, and p i ' is the probability of the ith symbol occurring in T.
Claim 54
Dependent Claim
100 words
Apparatus according to claim 38 wherein said function is I(T:R)-I(R:R) where ##EQU38## T is a test histogram; R is a reference histogram; I(T:R) is the information of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU39## I(R:R) is the information of R expressed in terms of R, and n i is the number of occurrences of the ith symbol in R.
Claim 55
Dependent Claim
100 words
Apparatus according to claim 38 wherein said function is H(T:R)-H(R:R) where ##EQU40## T is a test frequency histogram; R is a reference histogram; H(T:R) is the entropy of T expressed in terms of R; b is the base of the logarithm; m i is the number of occurrences of the ith symbol in T; p i is the probability of the ith symbol occurring in R; Q is the number of different symbols in T; ##EQU41## H(R:R) is the entropy of R expressed in terms of ##EQU42## n i is the number of occurrences of the ith symbol in R.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1989-01-27 | 1989-07-29 | 1990-01-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1993-01-27 | 1993-07-29 | 1994-01-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1997-01-27 | 1997-07-29 | 1998-01-28 | $7700.00 | Window Closed / Lapsed |